Skip to content

Commit 3f2eff0

Browse files
authored
Merge pull request #542 from snakers4/snakers4-patch-1
Update README.md
2 parents 2fff4b8 + 3a25110 commit 3f2eff0

File tree

1 file changed

+18
-11
lines changed

1 file changed

+18
-11
lines changed

README.md

Lines changed: 18 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -32,21 +32,28 @@ https://user-images.githubusercontent.com/36505480/144874384-95f80f6d-a4f1-42cc-
3232
<details>
3333
<summary>Dependencies</summary>
3434

35-
System requirements to run python examples:
36-
- `python 3.8+`
37-
- 1G+ RAM
38-
- not too outdated cpu
35+
System requirements to run python examples on `x86-64` systems:
36+
37+
- `python 3.8+`;
38+
- 1G+ RAM;
39+
- A modern CPU with AVX, AVX2, AVX-512 or AMX instruction sets.
3940

4041
Dependencies:
41-
- `torch>=1.12.0`
42-
- `torchaudio>=0.12.0` (for I/O functionalities only)
43-
- `onnxruntime>=1.16.1` (for ONNX model usage)
4442

45-
Silero VAD uses torchaudio library for audio file I/O functionalities, which are torchaudio.info, torchaudio.load, and torchaudio.save, so a proper audio backend is required:
43+
- `torch>=1.12.0`;
44+
- `torchaudio>=0.12.0` (for I/O functionalities only);
45+
- `onnxruntime>=1.16.1` (for ONNX model usage).
46+
47+
Silero VAD uses torchaudio library for audio I/O (`torchaudio.info`, `torchaudio.load`, and `torchaudio.save`), so a proper audio backend is required:
4648

47-
- Option №1 - [**FFmpeg**](https://www.ffmpeg.org/) backend. `conda install -c conda-forge 'ffmpeg<7'`
48-
- Option №2 - [**sox_io**](https://pypi.org/project/sox/) backend. `apt-get install sox`, TorchAudio is tested on libsox 14.4.2.
49-
- Option №3 - [**soundfile**](https://pypi.org/project/soundfile/) backend. `pip install soundfile`
49+
- Option №1 - [**FFmpeg**](https://www.ffmpeg.org/) backend. `conda install -c conda-forge 'ffmpeg<7'`;
50+
- Option №2 - [**sox_io**](https://pypi.org/project/sox/) backend. `apt-get install sox`, TorchAudio is tested on libsox 14.4.2;
51+
- Option №3 - [**soundfile**](https://pypi.org/project/soundfile/) backend. `pip install soundfile`.
52+
53+
If you are planning to run the VAD using solely the `onnx-runtime`, it will run on any other system architectures where onnx-runtume is [supported](https://onnxruntime.ai/getting-started). In this case please note that:
54+
55+
- You will have to impolement the I/O;
56+
- You will have to adapt the existing wrappers / examples / post-processing for your use-case.
5057

5158
</details>
5259

0 commit comments

Comments
 (0)